TestSetup

Exploratory analysis of Retail Trade Sales

Goals

• Reproduce the Index of the Canadian Economic Dashboard and COVID-19
• Identify data tables and vectors for the dashboard

Comments

• Time series from Canadian Economic Dashboard and COVID-19 at https://www150.statcan.gc.ca/n1/pub/71-607-x/71-607-x2020009-eng.htm
• There are 16 indicators

```r
suppressMessages(library(cansim))
suppressMessages(library(ggplot2))
suppressMessages(library(dplyr))
suppressMessages(library(plotly))
source(\../src/utils.R\)

<!-- rnb-source-end -->

<!-- rnb-chunk-end -->


<!-- rnb-text-begin -->


## Extract the Data

<!-- rnb-text-end -->


<!-- rnb-chunk-begin -->


<!-- rnb-source-begin eyJkYXRhIjoiYGBgclxudmVjdG9yX25hbWVzIDwtIGMoXG4gIFwidjY1MjAxMjEwXCIsIFwidjQxNjkwOTczXCIsIFwidjIwNjI4MDlcIiwgXCJ2MTAwMTgyNzI2NVwiLFxuICBcInYxMDAxODI2NjUzXCIsIFwidjUyMzY3MDk3XCIsIFwidjQzOTE1MDVcIiwgXCJ2ODAwNDUwXCIsXG4gIFwidjMyODU4ODU4XCIsIFwidjMyODU4ODY1XCIsIFwidjMyODU4ODcyXCIsIFwidjc0ODY5XCIsIFwidjEyOTQ0OVwiLFxuICBcInYxMjk0NjBcIiwgXCJ2MTI5NDcyXCIsIFwidjEyOTQ4MlwiXG4pXG5sZW5ndGgodmVjdG9yX25hbWVzKVxuYGBgIn0= -->

```r
vector_names <- c(
  "v65201210", "v41690973", "v2062809", "v1001827265",
  "v1001826653", "v52367097", "v4391505", "v800450",
  "v32858858", "v32858865", "v32858872", "v74869", "v129449",
  "v129460", "v129472", "v129482"
)
length(vector_names)

[1] 16

vector_descr <- c(
  "RealGDP", "CPI", "Employment [pers]", "Int. merchendise trade Exp. [$]",
  "Int. merchendise trade Imp. [$]", "Retail Sales [$]", "hours worked",
  "Manufact. sales [$]", "Aircraft domestic [#]", "Aircraft transborder [#]",
  "Aircraft int other [#]", "Railway carloads [tons]", "Travelers US [pers]",
  "Travelers other country [pers]", "CA resident US [pers]",
  "CAresident other country [pers]"
)
names(vector_descr) <- vector_names

I expect this date to be before the start of all time series/vectors.

start_date <- "1900-01-01"

Retrieve all vectors. They are concatunated along axis 0.

vectors <- get_cansim_vector(vector_names, start_date)

`as.tibble()` is deprecated as of tibble 2.0.0.
Please use `as_tibble()` instead.
The signature and semantics have changed, see `?as_tibble`.
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.

dim(vectors)

[1] 7506    9

retail_sales <- get_cansim("20-10-0008-01")
hours_worked <- get_cansim("14-10-0289-01")

Preprocessing

Normalization all indicators so that December 2019 = 100

vectors$REF_DATE = as.Date(vectors$REF_DATE)

head(vectors)

vector_names[1]

[1] "v65201210"

length(vector_names)

[1] 16

indicators1 <- vector(length=16)
for (i in 1:length(vector_names)) {
  #print(i)
  indicator = filter(vectors, VECTOR == vector_names[i])
  ref_value = indicator$VALUE[indicator$REF_DATE == as.Date('2019-12-01')]
  indicator$VALUE_INDEX = 100. * indicator$VALUE/ref_value
  if (i == 1) {indicators = indicator}
  else {indicators <- rbind(indicators, indicator)}
  # indicators1[i]  <- indicator
}

head(indicators)

indicators$descr <- sapply(indicators$VECTOR, function(x) {
  vector_descr[x][[1]]
})

Canadian Economic Dashboard

Retail Sales & Hours Worked

p <- ggplot(indicators, aes(x=REF_DATE, y=VALUE_INDEX)) + geom_line((aes(group=descr, color=descr))) +
  scale_x_date(date_breaks="2 month", date_labels="%b %Y", limits = as.Date(c('2019-01-01','2020-06-01'))) + scale_y_continuous(breaks=seq(0, 180,20), limits= c(0, 180)) + labs(title='Index, December 2019=100', x='', y='')
ggplotly(p)

retail_sales_plot = ggplot() + geom_line(data=retail_sales_can, aes(x=REF_DATE, y=VALUE_INDEX, color='green'))
hours_worked_plot = geom_line(data=hours_worked_industries, aes(x=REF_DATE, y=VALUE_INDEX, color='blue')) 

plot = retail_sales_plot +  hours_worked_plot + scale_x_date(date_breaks="2 month", date_labels="%b %Y", limits = as.Date(c('2019-01-01','2020-06-01'))) + scale_y_continuous(breaks=seq(70, 105,5), limits= c(70, 105)) + scale_color_manual(labels = c("Retail trade sales (dollars)", "Actual hours worked"), values = c("blue", "red")) + labs(color='Legend')
plot
#ggplotly(plot)

All Time Series

< - 

#select(hours_worked_plot, c("VALUES"))
hours_worked_industries %>% select(REF_DATE, VALUE_INDEX)

ggplot() + geom_line(data=hours_worked_industries, aes(x=REF_DATE, y=VALUE_INDEX))